Using Embeddings to Correct for Unobserved Confounding in Networks

2019/02/11 by Victor Veitch, Zhaoran Wang, Veitch, Victor +4 · 6 citations
Computer Science · Mathematics · #Advanced Causal Inference Techniques #Advanced Graph Neural Networks #Bayesian Modeling and Causal Inference #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1902.04114

An earlier version also addressed the use of text embeddings. That material has been expanded and moved to arxiv:1905.12741, "Using Text Embeddings for Causal Inference"

openalex publication_date 2019/02/11 · arxiv created 2019/05/31 · arxiv updated 2019/06/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We consider causal inference in the presence of unobserved confounding. We study the case where a proxy is available for the unobserved confounding in the form of a network connecting the units. For example, the link structure of a social network carries information about its members. We show how to effectively use the proxy to do causal inference. The main idea is to reduce the causal estimation problem to a semi-supervised prediction of both the treatments and outcomes. Networks admit high-quality embedding models that can be used for this semi-supervised prediction. We show that the method yields valid inferences under suitable (weak) conditions on the quality of the predictive model. We validate the method with experiments on a semi-synthetic social network dataset. Code is available at github.com/vveitch/causal-network-embeddings.

Citations

• Estimation of Regression Coefficients When Some Regressors are not Always Observed
• Constructing Inverse Probability Weights for Marginal Structural Models
• Homophily and Contagion Are Generically Confounded in Observational Social Network Studies
• The central role of the propensity score in observational studies for causal effects
• The Class of Random Graphs Arising from Exchangeable Random Measures
• Double/Debiased/Neyman Machine Learning of Treatment Effects
• Causal Effect Inference with Deep Latent-Variable Models
• Inductive Representation Learning on Large Graphs
• A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications
• Adapting Text Embeddings for Causal Inference

Cited by

• Population-Scale Network Embeddings Expose Educational Divides in Network Structure Related to Right-Wing Populist Voting
• Desiderata for Representation Learning: A Causal Perspective
• On the Intersection of Analytical Sociology and Computational Social Science
• Counterfactual Evaluation of Treatment Assignment Functions with Networked Observational Data
• Adjustment for Confounding using Pre-Trained Representations
• Identifiability of causal effects with multiple causes and a binary outcome
• Detecting Social Influence in Event Cascades by Comparing Discriminative Rankers

Related

• Learning Individual Causal Effects from Networked Observational Data
• Causal Inference Under Interference And Network Uncertainty
• Causal inference with misspecified network interference structure
• Learning Belief Network Structure From Data under Causal Insufficiency
• Identification and Estimation of Causal Effects from Dependent Data